def pls_crossval(X, y, n_comp, **kwargs):
opt_comp = optimal_n_comp(X, y, n_comp)
variance_explained(X, y, n_comp)
# to perform variable selection from regression with whole dataset
X_train_0_sel = pip_sel["variable_selection"].transform(X_train_0)
X_test_0_sel = pip_sel["variable_selection"].transform(X_test_0)
data_en_sel = {"X": X_train_0_sel, "y": y_train, "X_test": X_test_0_sel, "y_test": y_test}
# %%
# variance explained and MSECV for train and test set for each PLS component
var, comp = variance_explained(X_train_0, y_train, plot=False)
var_2, comp_2 = variance_explained(X_test_0, y_test, plot=False)
extra_plot_variance_explained(var, comp, var_2, comp_2)
mse, comp = mse_minimum(X_train_0, y_train, plot=False)
mase_2, comp_2 = mse_minimum(X_test_0, y_test, plot=False)
extra_plot_mse(mse, comp, mase_2, comp_2)
# %%
# variance explained and MSECV for train and test set for each component
var, comp = variance_explained(X_train_0_sel, y_train, plot=False)
var_2, comp_2 = variance_explained(X_test_0_sel, y_test, plot=False)
extra_plot_variance_explained(var, comp, var_2, comp_2)
mse, comp = mse_minimum(X_train_0, y_train, plot=False)
mase_2, comp_2 = mse_minimum(X_test_0, y_test, plot=False)
extra_plot_mse(mse, comp, mase_2, comp_2)
pip_dev0 = Pipeline(
[
("scaleing_X", GlobalStandardScaler()),
("scatter_correction", EmscScaler()),
("smmothing", SavgolFilter(polyorder=2, deriv=0)),
#("variable_selection", EnetSelect())
]
)
X_train_0 = pip_dev0.fit_transform(X_train, y_train)
X_test_0 = pip_dev0.transform(X_test)
# %%
variance_explained(X_train_0, y_train)
# %%
mse_minimum(X_train_0, y_train)
# %%
def pls_crossval(X, y, n_comp, **kwargs):
# fits a pls model with a given number of components
model = pls_regression(X, y, n_comp)
# calculated score and mse from given model
pls_scores(X, y, model)
return model
"""returns a model with the optimsed number of pls components"""
# returns n_comp with lowest loss
opt_comp = optimal_n_comp(X, y, n_comp, plot=plot)
# performs regression with n_comp
opt_model = pls_regression(X,y, opt_comp, plot=plot)
# returns regression scores
pls_scores(X,y, opt_model)
return opt_model
# %%
variance_explained(X_train_en, y_train, n_comp=20, plot=True)
variance_explained(X_train_pip, y_train, n_comp=20, plot=True)
# %%
# %%
model_en = pls_regression(**data_en, n_comp =3)
model_pip = pls_regression(**data_pip, n_comp =2)
# %%